Skip to content
← Back to explorer

HFEPX Hub

Math Or Multilingual Papers

Updated from current HFEPX corpus (Feb 27, 2026). 200 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Ranking. Frequent quality control: Calibration. Frequently cited benchmark: MATH. Common metric signal: accuracy. Use this page to compare protocol setup, judge behavior, and labeling design decisions before running new eval experiments. Newest paper in this set is from Feb 26, 2026.

Papers: 200 Last published: Feb 26, 2026 Global RSS Tag RSS
MathMultilingual

Research Narrative

Grounded narrative Model: deterministic-grounded Source: persisted

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 200 papers for Math Or Multilingual Papers. Dominant protocol signals include automatic metrics, simulation environments, human evaluation, with frequent benchmark focus on MATH, Retrieval and metric focus on accuracy, cost. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.

Why This Matters For Eval Research

Protocol Takeaways

Benchmark Interpretation

  • MATH appears in 10% of hub papers (20/200); use this cohort for benchmark-matched comparisons.
  • Retrieval appears in 8% of hub papers (16/200); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 27.5% of hub papers (55/200); compare with a secondary metric before ranking methods.
  • cost is reported in 10% of hub papers (20/200); compare with a secondary metric before ranking methods.

Researcher Checklist

  • Close gap on Papers with explicit human feedback. Coverage is a replication risk (9.5% vs 45% target).
  • Close gap on Papers reporting quality controls. Coverage is a replication risk (4.5% vs 30% target).
  • Maintain strength on Papers naming benchmarks/datasets. Coverage is strong (35% vs 35% target).
  • Maintain strength on Papers naming evaluation metrics. Coverage is strong (45% vs 35% target).
  • Close gap on Papers with known rater population. Coverage is a replication risk (9% vs 35% target).
  • Close gap on Papers with known annotation unit. Coverage is a replication risk (8% vs 35% target).

Papers with explicit human feedback

Coverage is a replication risk (9.5% vs 45% target).

Papers reporting quality controls

Coverage is a replication risk (4.5% vs 30% target).

Papers naming benchmarks/datasets

Coverage is strong (35% vs 35% target).

Papers naming evaluation metrics

Coverage is strong (45% vs 35% target).

Papers with known rater population

Coverage is a replication risk (9% vs 35% target).

Papers with known annotation unit

Coverage is a replication risk (8% vs 35% target).

Suggested Reading Order

  1. 1. Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  2. 2. AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  3. 3. Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  4. 4. InnerQ: Hardware-aware Tuning-free Quantization of KV Cache for Large Language Models

    Adds automatic metrics for broader coverage within this hub.

  5. 5. A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

    Adds automatic metrics for broader coverage within this hub.

  6. 6. NoRA: Breaking the Linear Ceiling of Low-Rank Adaptation via Manifold Expansion

    Adds automatic metrics for broader coverage within this hub.

  7. 7. Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching

    Adds automatic metrics for broader coverage within this hub.

  8. 8. Effective QA-driven Annotation of Predicate-Argument Relations Across Languages

    Adds automatic metrics for broader coverage within this hub.

Known Limitations

  • Only 4.5% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (9% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.

Research Utility Links

human_eval vs automatic_metrics

both=1, left_only=6, right_only=183

1 papers use both Human Eval and Automatic Metrics.

automatic_metrics vs simulation_env

both=3, left_only=181, right_only=10

3 papers use both Automatic Metrics and Simulation Env.

simulation_env vs human_eval

both=0, left_only=13, right_only=7

0 papers use both Simulation Env and Human Eval.

Benchmark Brief

MATH

Coverage: 20 papers (10%)

20 papers (10%) mention MATH.

Examples: Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning , Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards , RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models

Benchmark Brief

Retrieval

Coverage: 16 papers (8%)

16 papers (8%) mention Retrieval.

Examples: AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning , Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance , Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads

Benchmark Brief

GSM8K

Coverage: 13 papers (6.5%)

13 papers (6.5%) mention GSM8K.

Examples: InnerQ: Hardware-aware Tuning-free Quantization of KV Cache for Large Language Models , Black-Box Reliability Certification for AI Agents via Self-Consistency Sampling and Conformal Calibration , Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference

Metric Brief

accuracy

Coverage: 55 papers (27.5%)

55 papers (27.5%) mention accuracy.

Examples: AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning , InnerQ: Hardware-aware Tuning-free Quantization of KV Cache for Large Language Models , Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching

Metric Brief

cost

Coverage: 20 papers (10%)

20 papers (10%) mention cost.

Examples: Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching , Sparsity Induction for Accurate Post-Training Pruning of Large Language Models , Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"?

Metric Brief

latency

Coverage: 11 papers (5.5%)

11 papers (5.5%) mention latency.

Examples: Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding? , InnerQ: Hardware-aware Tuning-free Quantization of KV Cache for Large Language Models , Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching

Most Cited In This Hub

Fast path to methods with the strongest citation traction in this scope.

Papers: Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning , AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning , Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

Most Recent

Fast path to latest protocol changes and newly published evaluation setups.

Papers: Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning , AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning , Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

Best Protocol Detail

Papers with explicit rater/unit metadata and quality-control signals for reproducibility.

Papers: Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning , AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning , Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

Top Papers

Related Hubs